Related papers: ROSE: A Recognition-Oriented Speech Enhancement Fr…
Typical high quality text-to-speech (TTS) systems today use a two-stage architecture, with a spectrum model stage that generates spectral frames and a vocoder stage that generates the actual audio. High-quality spectrum models usually…
Target Speaker Automatic Speech Recognition (TS-ASR) aims to transcribe the speech of a specified target speaker from multi-speaker mixtures in cocktail party scenarios. Recent advancement of Large Audio-Language Models (LALMs) has already…
Target Sound Extraction (TSE) focuses on the problem of separating sources of interest, indicated by a user's cue, from the input mixture. Most existing solutions operate in an offline fashion and are not suited to the low-latency causal…
The Transformer self-attention network has recently shown promising performance as an alternative to recurrent neural networks (RNNs) in end-to-end (E2E) automatic speech recognition (ASR) systems. However, the Transformer has a drawback in…
Research on multilingual speech recognition remains attractive yet challenging. Recent studies focus on learning shared structures under the multi-task paradigm, in particular a feature sharing structure. This approach has been found…
Even though the large-scale language models have achieved excellent performances, they suffer from various adversarial attacks. A large body of defense methods has been proposed. However, they are still limited due to redundant attack…
This review paper provides a comprehensive analysis of recent advances in automatic speech recognition (ASR) with bidirectional encoder representations from transformers BERT and connectionist temporal classification (CTC) transformers. The…
Synthetic aperture radar automatic target recognition (SAR ATR) is of considerable importance in marine navigation and disaster monitoring. However, the coherent speckle noise inherent in SAR imagery often obscures salient target features,…
End-to-end Automatic Speech Recognition (ASR) systems based on neural networks have seen large improvements in recent years. The availability of large scale hand-labeled datasets and sufficient computing resources made it possible to train…
Audio-visual speech separation methods aim to integrate different modalities to generate high-quality separated speech, thereby enhancing the performance of downstream tasks such as speech recognition. Most existing state-of-the-art (SOTA)…
This paper presents a novel algorithm for building an automatic speech recognition (ASR) model with imperfect training data. Imperfectly transcribed speech is a prevalent issue in human-annotated speech corpora, which degrades the…
Conversational speech normally is embodied with loose syntactic structures at the utterance level but simultaneously exhibits topical coherence relations across consecutive utterances. Prior work has shown that capturing longer context…
Unsupervised speech recognition (unsupervised ASR) aims to learn the ASR system with non-parallel speech and text corpus only. Wav2vec-U has shown promising results in unsupervised ASR by self-supervised speech representations coupled with…
End-to-end modeling (E2E) of automatic speech recognition (ASR) blends all the components of a traditional speech recognition system into a unified model. Although it simplifies training and decoding pipelines, the unified model is hard to…
In this study, we investigate the benefits of domain-specific self-supervised pre-training for both offline and streaming ASR in Air Traffic Control (ATC) environments. We train BEST-RQ models on 4.5k hours of unlabeled ATC data, then…
Aligning acoustic and linguistic representations is a central challenge to bridge the pre-trained models in knowledge transfer for automatic speech recognition (ASR). This alignment is inherently structured and asymmetric: while multiple…
Recently, attention-based encoder-decoder (AED) models have shown high performance for end-to-end automatic speech recognition (ASR) across several tasks. Addressing overconfidence in such models, in this paper we introduce the concept of…
Automatic Speech Recognition (ASR), as the assistance of speech communication between pilots and air-traffic controllers, can significantly reduce the complexity of the task and increase the reliability of transmitted information. ASR…
Transformer-based end-to-end (E2E) automatic speech recognition (ASR) systems have recently gained wide popularity, and are shown to outperform E2E models based on recurrent structures on a number of ASR tasks. However, like other E2E…
Recently, Automatic Speech Recognition (ASR) systems (e.g., Whisper) have achieved remarkable accuracy improvements but remain highly sensitive to real-world unseen data (data with large distribution shifts), including noisy environments…